Explore no more: Improved high-probability regret bounds for non-stochastic bandits - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

Explore no more: Improved high-probability regret bounds for non-stochastic bandits

Gergely Neu
  • Fonction : Auteur correspondant
  • PersonId : 961179

Connectez-vous pour contacter l'auteur

Résumé

This work addresses the problem of regret minimization in non-stochastic multi-armed bandit problems, focusing on performance guarantees that hold with high probability. Such results are rather scarce in the literature since proving them requires a large deal of technical effort and significant modifications to the standard, more intuitive algorithms that come only with guarantees that hold on expectation. One of these modifications is forcing the learner to sample arms from the uniform distribution at least Ω(√ T) times over T rounds, which can adversely affect performance if many of the arms are suboptimal. While it is widely conjectured that this property is essential for proving high-probability regret bounds, we show in this paper that it is possible to achieve such strong results without this undesirable exploration component. Our result relies on a simple and intuitive loss-estimation strategy called Implicit eXploration (IX) that allows a remarkably clean analysis. To demonstrate the flexibility of our technique, we derive several improved high-probability bounds for various extensions of the standard multi-armed bandit framework. Finally, we conduct a simple experiment that illustrates the robustness of our implicit exploration technique.
Fichier principal
Vignette du fichier
IX_nips_final.pdf (398.4 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01223501 , version 1 (02-11-2015)

Identifiants

  • HAL Id : hal-01223501 , version 1

Citer

Gergely Neu. Explore no more: Improved high-probability regret bounds for non-stochastic bandits. Advances on Neural Information Processing Systems 28 (NIPS 2015), Dec 2015, Montreal, Canada. pp.3150-3158. ⟨hal-01223501⟩
246 Consultations
100 Téléchargements

Partager

Gmail Facebook X LinkedIn More